AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Predicting mutational effects on protein-protein binding via a side-chain diffusion probabilistic model

Shiwei Liu, Tian Zhu, Milong Ren, Yu Chungong, Dongbo Bu, Haicang Zhang

NeurIPS 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Protein interface and docking prediction · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add SidechainDiff pretrained representations to the ddG predictor (ablation)DiffAffinity · SKEMPI2 all mutationsPearson: 0.646 -> 0.669Improved
add SidechainDiff pretrained representations to the ddG predictor (ablation)DiffAffinity · SARS-CoV-2 RBD binding affinityPearson: 0.295 -> 0.466Improved
add SidechainDiff representations (ablation)DiffAffinity · SKEMPI2 multiple mutationsPearson: 0.613 -> 0.650Improved
use linear projection of SidechainDiff representation instead of IPA predictor head (ablation)DiffAffinity · SKEMPI2 all mutationsPearson: 0.669 -> 0.326Hurt
replace RDE flow-based representation with SidechainDiff diffusion representationddG predictor · SKEMPI2 all mutationsPearson: 0.632 -> 0.669Improved
replace ESM2 language model representation with SidechainDiffddG predictor · SKEMPI2 all mutationsPearson: 0.623 -> 0.669Improved
replace RDE with SidechainDiff for side-chain packingside-chain packing · PDB-REDOsteric clash number: 34.41 -> 27.70Improved
replace RDE with SidechainDiff for side-chain packingside-chain packing · PDB-REDOaverage chi MAE: 21.99 -> 22.06No clear effect
higher structural constraint (contact number 1-7 vs 11-19)SidechainDiff · PDB-REDO side-chain packingaverage chi error: 28.70 -> 15.43Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy